Shu Li

Ph.D. Candidate in Computer Science | AI & Machine Learning Researcher
West Lafayette, US.

About

Ph.D. Candidate in Computer Science with a robust background in AI4Science, specializing in structural biology, machine learning, deep learning, and graph neural networks. Proven ability to conduct cutting-edge research, demonstrated through multiple publications in top-tier AI conferences. Adept at leveraging advanced computational methods and analytical skills to drive innovation in complex problem domains.

Work

The Hong Kong University of Science and Technology
|

Visiting Student, Department of Computer Science and Engineering

→

Summary

Engaged in advanced research within AI4Science, with a particular focus on structural biology, under the mentorship of Prof. Yu Zhang.

Highlights

Contributed to research initiatives at the intersection of Artificial Intelligence and structural biology.

Collaborated with faculty on cutting-edge computational methods for scientific applications.

Nanjing University
|

Teaching Assistant, Discrete Mathematics

→

Summary

Provided academic support and instruction for undergraduate students in Discrete Mathematics.

Highlights

Facilitated learning for undergraduate students in Discrete Mathematics, enhancing comprehension of complex topics.

Assisted with grading assignments and providing constructive feedback.

Volunteer

European Conference on Artificial Intelligence (ECAI)
|

Program Committee Member

→

Summary

Contributed to the peer-review process for submitted papers at a leading international AI conference.

Highlights

Reviewed and evaluated research papers for technical merit and contribution to the field of AI.

Contributed to upholding the quality and integrity of conference proceedings.

Education

Purdue University

→

Ph.D.

Computer Science

Grade: 3.96/4.00

Courses

CS 58000: Algorithm Design and Analysis

CS 58800: Operating Systems

CS 53600: Data Communication and Networking

CS 59200-ATK: Advanced Topics in Machine Learning/AI

CS 59300-TDA: Topological Data Analysis

CS 59200-DML: Deep Machine Learning

Nanjing University

→

M.Sc.

Computer Science and Technology

Grade: 3.67/4.00

Courses

C Programming

Machine Learning

Data Mining

Introduction to Computer Vision

Python Programming

Introduction to Artificial Intelligence

Wuhan University

→

B.Sc.

Information and Computational Science

Grade: 3.44/4.00

Publications

Computational Methods for Bimolecular Structure Modeling for Cryo-EM

Published by

Taylor & Francis

Summary

Co-authored a chapter in 'Cryo-Electron Microscopy in Structural Biology' detailing computational methods for bimolecular structure modeling using Cryo-EM data.

Polynomial Width is Sufficient for Set Representation with High-dimensional Features

Published by

International Conference on Learning Representations (ICLR)

Summary

Co-authored a paper demonstrating the sufficiency of polynomial width for representing sets with high-dimensional features, presented at ICLR.

Multi-View Representation Learning with Manifold Smoothness

Published by

Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI '21)

Summary

Authored a paper on multi-view representation learning incorporating manifold smoothness principles, presented at AAAI.

Co-GCN for Multi-view Semi-supervised Learning

Published by

Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI '20)

Summary

Authored a paper introducing Co-GCN, a novel approach for multi-view semi-supervised learning, presented at AAAI.

MiSC: Mixed Strategies Crowdsourcing

Published by

Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI '19)

Summary

Co-authored a paper on Mixed Strategies Crowdsourcing, presented at IJCAI.

Languages

English

Proficient

Chinese (Mandarin)

Native

Skills

Programming Languages

Python, C/C++, Julia, MATLAB.

Machine Learning & AI

Deep Learning, Artificial Intelligence, Graph Neural Networks (GNNs), Multi-view Learning, Semi-supervised Learning, Hypergraph Diffusion, Computer Vision, Data Mining, Reinforcement Learning.

Scientific Computing & Data Analysis

PyTorch, NumPy, SciPy, Numerical Linear Algebra, Numerical Analysis, Topological Data Analysis.

Tools & Platforms

LaTeX, Git, GitHub.

Core Computer Science

Algorithm Design and Analysis, Operating Systems, Data Communication and Networking.

Interests

Professional Organizations

China Computer Federation (CCF), Association for the Advancement of Artificial Intelligence (AAAI).

Projects

Equivariant Neural Operator for Hypergraph Diffusion

→

Summary

Designed and developed an equivariant neural operator to model hypergraph diffusion, leveraging insights from ADMM (Alternating Direction Method of Multipliers).

GNNs in Multi-view Learning

→

Summary

Pioneered the design of state-of-the-art multi-view learning algorithms within the deep learning paradigm, focusing on Graph Convolutional Networks (GCNs).